Table 5.

The different datasets that may be involved in a simulation study

Dataset	Description and Notes
Simulated	A dataset of size n obs produced with some element of random‐number generation, to
	which one or more methods are applied to produce some quantity relating to
	the target of the study, such as an estimate of θ.
Estimatesa	Dataset containing n sim summaries of information from
	repetitions (eg,  $\widehat{\theta }$, $\widehat{\text{SE}}(\widehat{\theta })$, indication of hypothesis rejection)
	for each combination of data‐generating mechanism, method, and target (eg, each estimand).
States	Dataset of containing n sim + 1 random‐number‐generator states: the
	start state for each simulated dataset and the final state (see Section 4.1).
Performance measures	Dataset containing estimated performance and Monte Carlo standard
	errors for each data‐generating mechanism, method and target.

^a or corresponding summaries for nonestimand targets